Search

The work proposed a method for recognising the green grapes in the orchard based on multi-source image fusion. First, the acquired multi-source images were denoised based on median filtering and wavelet transform. After extracting the feature points by the improved SURF (speeded up robust features) method, the registration was completed based on the consistency of feature offset and the affine relationship between images. The registered multi-source images were fused based on the CS (compressed sensing) and NSCT-DWT (non-down sampled contourlet transform-discrete wavelet transform). Then the MI-OPT (mutual-information optimal threshold) and the minimum circumscribed rectangle were used to segment the fused images and recognise fruits. The experimental results showed that the information of the target fruits in the fused images was complete. Therefore, compared with the K-means method using colour components of the visible light image and the OTSU (proposed by Nobuyuki Otsu and named after him) method based on near-infrared image, the fruit region obtained by the algorithm in the work was complete. On this basis, the average recognition rate of green grapes reached 92.1%. [ABSTRACT FROM AUTHOR]

• A network model (YOLO N) for the recognition of growth posture of peach young fruit in orchards was proposed. • The CA attention mechanism is adopted to solve the problem of near-color background. • A small target detection layer is added, and the PANeT structure is used as the extracted feature network. A network model was proposed for identifying the growth posture of young peach fruits in orchards (YOLO N) with the YOLOv5 network model in view of identifying the growth posture of young peach fruits in the natural growth state of orchards. First of all, Coordinate Attention (CA) was added based on the original backbone network due to the influence of peach young fruits on the near-color background to enhance the feature extraction ability of the image. Then, a small-target detection layer was added to the backbone network to optimize the detection effect of smaller young fruits. Finally, the rotating frame was selected to replace the original horizontal frame to detect the young fruits with directional attributes. Experiments showed that proposed YOLO N in the visual recognition of the growth posture of multi-directional peach young fruits had the average accuracy rate of the recognition of peach young fruit and the estimation error of its growth angle of 93.04% and ±3.94°, respectively. It has a good recognition effect, which provides a reference for the visual recognition of the growth posture of other young fruits and vegetables. [ABSTRACT FROM AUTHOR]

The discrimination the shape of overlapped apple images was investigated. A combination of procedures was used to form the process using basic image processing to obtain a complete fruit region within the collected apple image. The connected region in the fruit image was framed by horizontal minimum rectangle and the Euclidean distance method was used to calculate the distance of each fruit in the connected region. The grey value of distance image increases from the outside to the inside, and becomes the maximum in the centre of the fruit region. Thus, a horizontal and vertical projection curve was obtained. Using the improved local extremum method, the effective peaks were extracted from the curve smoothed by the moving average method. The shape of the overlapped apple was discriminated based on the number of peaks. To verify the effectiveness of algorithm, 30 apple images including overlapped fruits were selected from captured images for experiments. Result showed that the algorithm effectively discriminated overlapped shape of apple fruits, which was superior to the previous methods. • Horizontal and vertical projection curves based on Euclidean distance image. • A shape discriminant method for overlapped images. • Based on transverse and vertical projection curves. • Method was more reliable and effective than previous published methods. [ABSTRACT FROM AUTHOR]

• A method for apple growth morphology based on Mask RCNN + PointRend has been proposed. • SPPF structure, CA attention mechanism and PANet are introduced as improvements. • CWD algorithm is used for model distillation to improve the detection speed. Identifying apples with different growth forms is an urgent task to be solved by harvesting robots on the path to intelligence. A method based on Mask RCNN + PointRend was proposed for identifying apples with different growth forms in the orchard in the work. The SPPF structure and CA attention mechanism were introduced to the backbone network of the Mask RCNN + PointRend algorithm to improve network performance because of the complexity of the apple orchard. Meanwhile, a bottom-up pathway was introduced into the feature extraction network to enhance feature dissemination, reuse, and fitting. Finally, the number of model parameters was reduced to improve the detection speed, and the CWD algorithm was used for the knowledge distillation of the model. The improved algorithms were called Mask RCNN-Point and Mask RCNN-PointKD. The recognition accuracy of the two enhanced algorithms on the test set was 85.65 and 74.13%, respectively. Besides, average detection time per image was 93.67 and 62.1 ms, respectively. The work provides a reference for identifying apples with different growth forms. [ABSTRACT FROM AUTHOR]

Highlights • A segmentation method of merging after regions extraction for bagged apple image. • Normal-light fruit area oriented extraction based on CLAHE method. • Highlighted fruit area oriented extraction based on image reconstruction. Abstract Based on the own characteristics of bagged green apple image, the work designed an image segmentation method of bagged green apples which was combined after extraction of the normal light regions and highlighted regions of fruits. The contrast limited adaptive histogram equalization (CLAHE) algorithm was deepened fruit green region and improve edge definition in image, and then the R-B color difference image based on CLAHE image was obtained. The linear contrast of the original RGB image was enhanced to improve color difference in the normal light regions of fruits and leaves. The image after contrast enhancement was extracted in the region of R-B color difference image. Then the image was performed with OTSU segmentation algorithm and denoising to extract the normal light region of fruit. For the extraction of highlighted region of fruit in RGB images of bagged green apples, the main colors of image were first extracted. Then, the image was reconstructed with the main colors. The reconstructed and original images were subtracted and denoised to realize the extraction of the highlighted region of fruits. Finally, the complete fruit target region was obtained by combining the two extracted regions. The test results showed that we could obtain more complete fruit region of bagged green fruits based on the method in the work. [ABSTRACT FROM AUTHOR]

This work proposed a method to acquire regions of fruit, branch and leaf from red apple image in orchard. To acquire fruit image, R-G image was extracted from the RGB image for corrosive working, hole filling, subregion removal, expansive working and opening operation in order. Finally, fruit image was acquired by threshold segmentation. To acquire leaf image, fruit image was subtracted from RGB image before extracting 2G-R-B image. Then, leaf image was acquired by subregion removal and threshold segmentation. To acquire branch image, dynamic threshold segmentation was conducted in the R-G image. Then, the segmented image was added to fruit image to acquire adding fruit image which was subtracted from RGB image with leaf image. Finally, branch image was acquired by opening operation, subregion removal and threshold segmentation after extracting the R-G image from the subtracting image. Compared with previous methods, more complete image of fruit, leaf and branch can be acquired from red apple image with this method. [ABSTRACT FROM AUTHOR]

In order to resolve the problems of low efficiency and large separating difference in fault detection of lamp holders with single soldering lug, an image-detection-based defect detection method is presented in this paper. The selected image is first preprocessed, where the possible area of soldering lug is cut in this preprocessing to narrow the scope for subsequent partition with the consideration that the smooth surface of metal at lamp holder and black insulation glass may reflect the light. Then, the soldering lug is extracted by a series of processing including clustering partition. Based on this, the defects are detected by regional marking, area comparison, circularity and coordinate deviation. The experiment results show that the designed method is simple and practical to detect main quality defects of lamp holder with single soldering lug correctly and efficiently. [ABSTRACT FROM AUTHOR]

• A visual recognition method of apple growth morphology is proposed. • An improved YOLOv5 deep learning network (called YOLOv5-B) was proposed. • On the basis of YOLOv5, BiFPN-S and ACON-C are introduced as improvements. The work aimed at the visual identification of the growth forms of fruits to facilitate the subsequent use of different harvesting mechanisms for different growth forms of fruits by robots. The improved YOLOv5 deep learning algorithm was used to propose a visual identification method for the growth forms of apples in the orchard. Specifically, the feature extraction module of the YOLOv5 algorithm imitated the BiFPN model to propose the BiFPN-S structure. The spread of features and feature reuse were enhanced to better fit features. The improved algorithm was called YOLOv5-B. The network SiLU activation function was replaced with the ACON-C activation function to improve its network performance. The COCO data set was used to pre-train the network, and then the data set of the work was trained by the transfer learning method. After the training, the generated optimal model was applied for the visual-identification test of the growth of apple fruits. The results showed that the improved algorithm model considered high accuracy and real-time performance, with the map reaching 98.4% and the F1 value of 0.928. The average accuracy of identifying the growth forms of apples for the test set was 98.45%, and the processing speed was 71 FPS. [ABSTRACT FROM AUTHOR]

In complex driving scenarios, automated vehicles should behave reasonably and respond adaptively with high computational efficiency. In this paper, a computational efficient motion planning method is proposed, which considers traffic interaction and accelerates calculation. Firstly, the behavior is decided by connecting the points on the unequally divided road segments and lane centerlines, which simplifies the decision-making process in both space and time span. Secondly, as the dynamic vehicle model with changeable longitudinal velocity is considered in the trajectory generation module, the C/GMRES algorithm is used to accelerate the calculation of trajectory generation and realize on-line solving in nonlinear model predictive control. Meanwhile, the motion of other traffic participants is more accurately predicted based on the driver's intention and kinematics vehicle model, which enables the host vehicle to obtain a more reasonable behavior and trajectory. The simulation results verify the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

• Location method based on ensemble learning of convolutional neural networks (CNNs). • Predict any position by training ensemble model with partial sensing positions data. • Accurately locate pipeline leakage with mean absolute error of no more than 14.6 m. • Location resolution is as small as 10 m for Sagnac distributed fiber sensing system. • No need to demodulate and denoise interference signals. Aiming at the location problem of high-pressure pipeline leakage, this paper proposes a method for predicting the disturbed position of a Sagnac distributed optical fiber sensing system based on ensemble learning of convolutional neural networks (CNNs). A Stacking ensemble method is used to combine two different CNN models to improve the stability and location accuracy of the disturbance position prediction model. By training the prediction model using the spectrum features of interference signals generated by the disturbances at partial sensing positions, accurate prediction of an arbitrary disturbance position can be realized. The disturbance position prediction was carried out numerically on a sensing fiber with an effective length of 8.5 km. Simulation results show that a mean absolute error of no more than 14.6 m and a location resolution of 10 m are achieved. The method is insensitive to noise, low in system complexity, simple in data processing and accurate in location results. [ABSTRACT FROM AUTHOR]

Presently, the combination of graph convolutional networks (GCN) with resting-state functional magnetic resonance imaging (rs-fMRI) data is a promising approach for early diagnosis of autism spectrum disorder (ASD). However, the prevalent approach involves exclusively full-brain functional connectivity data for disease classification using GCN, while overlooking the prior information related to the functional connectivity of brain subnetworks associated with ASD. Therefore, in this study, the multiple functional connectivity–based graph convolutional network (MFC-GCN) framework is proposed, using not only full brain functional connectivity data but also the established functional connectivity data from networks of key brain subnetworks associated with ASD, and the GCN is adopted to acquire complementary feature information for the final classification task. Given the heterogeneity within the Autism Brain Imaging Data Exchange (ABIDE) dataset, a novel External Attention Network Readout (EANReadout) is introduced. This design enables the exploration of potential subject associations, effectively addressing the dataset's heterogeneity. Experiments were conducted on the ABIDE dataset using the proposed framework, involving 714 subjects, and the average accuracy of the framework was 70.31%. The experimental results show that the proposed EANReadout outperforms the best traditional readout layer and improves the average accuracy of the framework by 4.32%. [ABSTRACT FROM AUTHOR]

Regarding the identification and location of bayberries in the natural environment, the work applied the dilated convolution to the res4b module of Mask RCNN backbone network—ResNet. The method was used to realize the accurate identification and segmentation of waxberry. First, we pre-trained the d -MRCNN network transformed by the dilated convolution with the COCO dataset. Then, through the migration learning method, the representative waxberry dataset was used to train the network for the identification and segmentation of waxberry. Finally, based on the same verification sample set, the work compared the Ostu and K-Means with the deep learning segmentation networks U-net and FCN. The result showed that the algorithm in this work was optimal, with the average detection accuracy and recall rate reaching 97 % and 91 %, respectively. It has high generalization in non-structural environment and better robustness with various forms. [ABSTRACT FROM AUTHOR]

• Apple image correction based on the adaptive Gamma method. • Using the basic image processing method to extract the complete fruit regions. • Obtaining the near-large fruit by the optimized iterative open operation method. It is appropriate for near-large fruit to be the first target of single-arm harvesting robot based on machine vision in each operation. The work introduced a method to obtain the near-large fruit from apple image in orchard. Firstly, the R-channel and G-channel images of orchard apple RGB (Red, Green, Blue) images were operated by the adaptive Gamma correction method to overcome the influence of natural illumination on subsequent image segmentation. After combination, the treatment process was formed by the basic image processing method such as corrosion, expansion, hole filling, and fixed threshold segmentation to obtain a complete, clean fruit area in the collected apple image. Finally, the near-large fruit was obtained from apple image of orchard based on the optimized iterative open operation. To verify the designed method, 30 apple images were selected according to strong to low light conditions from the captured images. Experimental results showed that the apple image after the adaptive Gamma correction was segmented to obtain the cleaner fruit region. The proposed method was used to obtain the correct near-large fruit with nearly real area. The optimized iterative open operation reduced the execution time of entire algorithm, with average and maximum reduction ratios of 70 and 84%, respectively. [ABSTRACT FROM AUTHOR]

Apple image segmentation based on convex hull center priori and Markov adsorption chain is proposed in this paper. First, the convex hull, containing Harris points of interest, is approximated as a significant target area. Significant measurements were performed using convex hull center priori to obtain a preliminary saliency map with binary segmentation. Foreground points in the salient region were selected as absorbing nodes for an adsorbing Markov chain, and the remaining points were transfer nodes for an absorbing Markov chain, thus strengthening the salient regions by constructing a Markov chain. An ideal saliency map was obtained by optimization. Finally, a threshold obtained using the Otsu algorithm was used for adaptive apple image segmentation of the salient region. A comparison of different algorithms shows that the method has some advantages in terms of performance and efficiency. [ABSTRACT FROM AUTHOR]

Twin delayed deep deterministic (TD3) policy gradient has several limitations when applied in planning a path in environment with a number of dilemmas according to our experiment, due to the complexity of the robot path planning task, the rate of convergence of TD3 algorithm is slow and the rate of collision is high. To address this problem, deep dense dueling twin delayed deep deterministic (D3-TD3) architecture is proposed, a method that preserves important information from cross-layer inputs through dense connections and divides the network into a value function and a dominance function, thus, allowing for faster convergence when solving complex tasks. Finally, a spatial model based on three-dimension (3D) point cloud is built, and simulation experimental results show that in static environment, the algorithm proposed in the paper has 40.6% fewer collisions compared to TD3, 30% fewer collisions compared to TD3-BC, 19.2% fewer collisions compared to Dueling TD3 and 17.4% fewer collisions compared to deep dense TD3. In dynamic and static environment, the algorithm proposed in the paper has 34.4% fewer collisions compared to TD3, 24% fewer collisions compared to TD3-BC, 6% fewer collisions compared to Dueling TD3 and 25% fewer collisions compared to deep dense TD3. [ABSTRACT FROM AUTHOR]

Highlights • A hierarchical approach decomposing a complex verification problem into simpler ones is proposed. • Use a system science tool called STAMP to help understand the nature of the control system to be verified. • A formal framework is brought up, so the overall safety property can be proved formally by proving sub-goals. • Arbitrary techniques and tools can be chosen to prove sub-goals if appropriate. Abstract Complexity is a major obstacle to apply formal verification techniques in industry. Assume-guarantee (AG) reasoning is a promising compositional verification approach to deal with complexity. Proper decomposition and assumption design is vital in AG reasoning. We are motivated by the fact that a good insight into the target system can help the formal verification. So, instead of trying to automate the AG reasoning process, an accident model called STAMP is adopted to help us get a better understanding of the safety control system to be verified and a strategy for decomposition and designing assumptions accordingly. This conceptual approach is exemplified by verifying a simplified train control system. [ABSTRACT FROM AUTHOR]

A bayberry image segmentation method based on salient object detection is proposed in this study. First, an image enhancement algorithm, homomorphic filtering, was used for light compensation. Second, superpixels were used as the basic unit in the subsequent significant calculation with the SLIC (simple linear iterative clustering) algorithm and were constructed as nodes in an Undirected Graphical Model G (V , E). Third, a two-stage scheme of saliency detection was proposed. In the first stage, the nodes on each boundary were separately ranked as query nodes. Then, four saliency maps were obtained using a MR (manifold ranking) method. After combining the four saliency maps, the saliency map of the first stage was acquired. In the second stage, binary segmentation was performed, based on the saliency map of the first stage to obtain the target query. Finally, binary segmentation was performed based on the saliency map with the Otsu's method to achieve the segmentation of bayberry images. The average values of Precision, Recall and F-measure in the proposed algorithm are 0.93, 0.83 and 0.90, respectively. Experimental results show that the proposed segmentation algorithm performs more effectively than Otsu's and K-means segmentation algorithms. Highlights • Homomorphic filtering was applied for light compensation and better segmentation. • A saliency map was established using manifold ranking for target detection. • Fruits were segmented without extracting colour, shape or texture features. [ABSTRACT FROM AUTHOR]

• Designed a agricultural residual film pollution monitoring system based on UAV. • Implemented autonomous random sampling on agricultural field surfaces using UAV. • The R2 of UAV evaluated film pollution and manual evaluation was 0.966. • The average monitoring and evaluation time of the system is 422.6 s. To evaluate residual film recovery quality and rapidly monitor residual film pollution in agricultural fields, a residual film pollution monitoring system based on UAV, ground station, and cloud server was proposed in this research. It integrated a random sampling point generation (RSPG) algorithm and a key-lock pairing (KLP) algorithm for fast planning of flight paths, and used the U-Net model to rapidly segment residual films from images and calculate residual film coverage. The results showed that the average deviation between the actual distance and the ideal distance of the randomly generated sampling points using the RSPG algorithm was 0.0733 m, and the average deviation of the azimuth angles was 0.2°. The KLP algorithm significantly reduced path planning time, while maintaining a high shortest path rate and reducing memory consumption. The U-Net model achieved an optimal mean intersection over union (MIOU) of 85.63 % on the test set. The simulation and field verification of the system found that automatic UAV path planning and rapid residual film image segmentation were achieved. The coefficient of determination (R2) between the predicted values and the manually labelled values was 0.966, and the root-mean-square error (RMSE) was 0.1173 %. The average relative error between the predicted residual film coverage and the manually labelled coverage was 11.55 %, and the average detection time of the monitoring system was 422.6 s. Therefore, the UAV-based residual film pollution monitoring system can realize integrated automatic sampling and rapid residual film pollution assessment. This study provides technical support for accurate assessment and control of residual film pollution. [ABSTRACT FROM AUTHOR]

• The expression of the gain matrix proposed by EKF is simplified. • The simplified gain matrix is exactly the same as the one proposed by CF. • CF is an approximation to EKF. • EKF is more stable than CF in low sampling applications. • CF relies more on the measurements of gyroscope for attitude determination. Extended Kalman Filter (EKF) and Complementary Filter (CF) are the two most commonly-used attitude determination algorithms in inertial and magnetic measurement units. It is known that the only difference between the a posterior attitude estimates provided by EKF and CF respectively is the gain matrix (GM) assigned to innovation for attitude update. Through mathematical derivation, it is concluded that the GM of EKF can be simplified to the one of CF, which means that CF is an approximation to EKF. Monte Carlo simulations were done to validate what influence of these simplifications is put on the performance of EKF. The main finding is EKF is more stable than CF in condition of low sampling rate, and hence CF must rely more on the measurements of gyroscope for attitude determination to improve its stability. [ABSTRACT FROM AUTHOR]

As a hot topic in railways, virtual coupling technology connects multiple trains (units) as a virtually coupled train set (VCTS) and aims to improve the performance of train operation by keeping a small following distance between successive units. For the desired performance, robust constraint satisfaction and stability are crucial properties of a VCTS. However, they are hard to be simultaneously guaranteed with uncertain train dynamics. To solve this problem, we propose a dual-mode robust model predictive control (DRMPC) approach. First, by considering uncertain actuator gains and resistance parameters, the VCTS operation is modeled with safety and input constraints. Then, we put forward a dual-mode scheme to adopt a controller from two candidates. Among this, we formulate a feedback controller through the analysis of local and string stability and adopt it in an admissible region to efficiently guarantee the crucial properties. To handle the rest cases with the risk of constraint dissatisfaction, an optimal controller is yielded by solving a constrained optimization framework employing the homothetic-tube technique. Specifically, local tubes are recursively constructed online by the set-membership prediction, while considering the tubes from the preceding unit. Next, the robust constraint satisfaction and stability of the VCTS are proved within the closed-loop implementation of DRMPC. Finally, experimental results verify the performance and advantages of the proposed approach on a VCTS. • A homothetic-tube-based robust MPC approach for VCTS. • Robust constraint satisfaction and stability with uncertain dynamics. • A dual-mode control scheme to save the computational consumption. [ABSTRACT FROM AUTHOR]

Intelligent bus system plays a key role in the modern smart city. The number of passengers in the buses or at the stations is necessary for making an optimal scheduling policy of public buses. We develop a crowd counting algorithm to provide the counting information for a bus dispatch system in a human–machine system. In consideration of the challenges (e.g., pedestrian occlusions, non-uniform crowd distributions, and scale variations) existed in hand-crafted features based crowd counting, a scale-distribution-aware multi-column convolutional neural network (SDA-MCNN) is presented to count crowds by summing up the output (denoted as the density map) of the SDA-MCNN. The SDA-MCNN is robust to scale variations by processing a crowd image with multiple convolutional neural network (CNN) columns and minimizing the per-scale loss. A weighted Euclidean loss is proposed to handle non-uniform crowd distributions. The loss can increase activations in dense regions and restrain activations in backgrounds. A new approach to estimate perspective maps of dense crowds is put forward to offer necessary information for generating density maps with human-shaped kernels. Evaluations on benchmarks are performed with other state-of-the-art counting approaches using deep neural networks. Comparative results verify the accuracy of our counting approach in challenging crowds. Evaluations on the real world BUS data reveal the accuracy of the proposed approach in counting passengers in spite of the complex environment. [ABSTRACT FROM AUTHOR]

Crowd counting from low-resolution images is a challenging task, in particular in the edge computing system. An embedded equipment is commonly incompetent at patch-based crowd counting with real-time performance. This work develops a real-time method to count passengers in a bus by using Nvidia TX2. The videos of entry are recorded by a camera up ahead, and the data suffer from severe occlusion, which makes designing handcrafted features difficult. The counting is performed by summing up pixel values of the density map estimated using a compact convolutional neural network (CCNN), which is robust to scale variations by employing skip connections. A weighted Euclidean loss is proposed to handle cluttered backgrounds and blurry foregrounds. The loss increases the activations in dense regions, but can restrain the activations in background regions. The counting results are further improved by smoothing, which utilizes constraints between consecutive frames. Comparisons with existing counting approaches, including patch-based and whole image-based approaches, are made on two benchmarking datasets. The results indicate the accuracy of CCNN in counting dense crowds. Moreover, the evaluated bus datasets verify the feasibility of CCNN in counting passengers from low-resolution input images with real-time performance on TX2. [ABSTRACT FROM AUTHOR]

Maximizing regenerative energy utilization is an important way to reduce substation energy consumption in subway systems. Timetable optimization and energy storage systems are two main ways to improve improve regenerative energy utilization, but they were studied separately in the past. To further improve energy conservation while maintaining a low cost, this paper presents a strategy to improve regenerative energy utilization by an integration of them, which determines the capacity of each Wayside Energy Storage System (WESS) and correspondingly optimizes the timetable at the same time. We first propose a dual-objective optimization problem to simultaneously minimize substation energy consumption and the total cost of WESS. Then, a mathematical model is formulated with the decision variables as the configuration of WESS and timetable. Afterwards, we design an ϵ -constraint method to transform the dual-objective optimization problem into several single-objective optimization problems, and accordingly design an improved artificial bee colony algorithm to solve them sequentially. Finally, numerical examples based on the actual data from a subway system in China are conducted to show the effectiveness of the proposed method. Experimental results indicate that substation energy consumption is effectively reduced by using WESS together with a correspondingly optimized timetable. Note that substation energy consumption becomes lower when the total size of WESS is larger, and timetable optimization further reduces it. A set of Pareto optimal solutions is obtained for the experimental subway line—based on which, decision makers can make a sensible trade-off between energy conservation and WESS investment accordingly to their preferences. [ABSTRACT FROM AUTHOR]

An attitude algorithm is used by a given magnetic and inertial measurement unit (MIMU) for weight fusion of the outputs of gyroscope and the outputs of the subunit constructed by accelerometer and magnetometer for attitude calculation of a rigid body. It has been proved that the weight assigned to the outputs of gyroscope determines the overall performances of attitude algorithm. A new weight adaptive regulation method based on Kalman filter and hidden Markov model is proposed, and then a new attitude algorithm is constructed by the integration of that method with recursive quaternion estimation algorithm. The authors' attitude algorithm is compared with some other related attitude algorithms in their experiments. With the outputs of the sensors in MTi as the inputs of the new attitude algorithm, the maximum attitude estimation errors in response to three‐dimensional random movements and the changes of their amplitudes are 2.85° and 6.82°, respectively, and the Allan variance of attitude drift in response to motionless conditions is 2.1×10−4°. Other attitude algorithms cannot simultaneously achieve similar dynamic and similar static performances comparing to their attitude algorithm. The results validate the overall performance improvement of their attitude algorithm. [ABSTRACT FROM AUTHOR]

Patients with attention-deficit/hyperactivity disorder (ADHD) have shown abnormal functional connectivity and network disruptions at the whole-brain static level. However, the changes in brain networks in ADHD patients from dynamic functional connectivity (DFC) perspective have not been fully understood. Accordingly, we executed DFC analysis on resting-state fMRI data of 25 ADHD patients and 27 typically developing (TD) children. A sliding window and Pearson correlation were used to construct the dynamic brain network of all subjects. The k -means+ + clustering method was used to recognize three recurring DFC states, and finally, the mean dwell time, the fraction of time spent for each state, and graph theory metrics were quantified for further analysis. Our results showed that ADHD patients had abnormally increased mean dwell time and the fraction of time spent in state 2, which reached a significant level (p < 0.05). In addition, a weak correlation between the default mode network was associated in three states, and the positive correlations between visual network and attention network were smaller than TD in three states. Finally, the integration of each network node of ADHD in state 2 is more potent than that of TD, and the degree of node segregation is smaller than that of TD. These findings provide new evidence for the DFC study of ADHD; dynamic changes may better explain the developmental delay of ADHD and have particular significance for studying neurological mechanisms and adjuvant therapy of ADHD. • Multiple recurring DFC patterns were first identified from resting state fMRI data of ADHD. • ADHD and TD had significant differences in mean dwell time and the fraction of time spent using DFC. • The degree of network integration and separation is related to different DFC states. [ABSTRACT FROM AUTHOR]

• A novel framework for the RDBM is proposed based on the predicted operation trajectory of the preceding train. • A cooperative collision-avoidance control methodology is proposed to ensure the safety and enhance the operation efficiency. • The DQN algorithm is introduced to learn the safe and efficient control strategy. • The effectiveness of the proposed approach is verified by experimental simulations To further improve the line transport capacity, virtual coupling has become a frontier hot topic in the field of rail transit. Specially, the safe and efficient following control strategy based on relative distance braking mode (RDBM) is one of the core technologies. This paper innovatively proposes a cooperative collision-avoidance control methodology, which can enhance the operation efficiency on the premise of ensuring the safety. Firstly, a novel framework for the RDBM based on the predicted trajectory of the preceding train is proposed for the train collision-avoidance control. To reduce the train following distance, a cooperative control model is further proposed and is formulated as a Markov decision process. Then, the Deep-Q-Network (DQN) algorithm is introduced to solve the efficient control problem by learning the safe and efficient control strategy for the following train where the critical elements of the reinforcement learning framework are designed. Finally, experimental simulations are conducted based on the simulated environment to illustrate the effectiveness of the proposed approach. Compared with the absolute distance braking mode (ADBM), the minimum following distance between the adjacent trains can be reduced by 70.23% on average via the proposed approach while the safety can be guaranteed. [ABSTRACT FROM AUTHOR]